Abstract-A learning environment generates massive knowledge by means of the services provided in MOOCs. Such knowledge is produced via learning actor interactions. This result is a motivation for researchers to put forward solutions for big data usage, depending on learning analytics techniques as well as the big data techniques relating to the educational field. In this context, the present article unfolds a uniform model to facilitate the exploitation of the experiences produced by the interactions of the pedagogical actors. The aim of proposing the said model is to make a unified analysis of the massive data generated by learning actors. This model suggests making an initial pre-processing of the massive data produced in an e-learning system, and it's subsequently intends to produce machine learning, defined by rules of measures of actors knowledge relevance. All the processing stages of this model will be introduced in an algorithm that results in the production of learning actor knowledge tree.Keywords-learning analytics, operational data, machine learning, big data analysis, knowledge management IntroductionCurrently, the field of education is flourishing rapidly throughout the world, due to the changes that have been occurring in this area with the implementation of Massive Open Online Courses MOOCs [1]. Great many research projects have been funded in order to draw the attention of researchers in this field to work on such massive data, conducting in-depth studies of MOOCs (COURSERA, OPEN ODX, etc.).MOOCs generate big data in the form of activity traces. Such data are of three various types, namely: structured, semi-structured and unstructured data. In [2], the author has conducted an in-depth study on the types of data generated by the interactions of educational actors in online learning systems. The structured data are those found in the databases; the semi-structured are those found in the XML and JSON files, whereas the unstructured are those found in documents, video recordings, audio, etc.iJET -Vol. 12, No. 11, 2017 151Big data analysis [3] represents the combination of big data techniques with learning analysis. This combination enables to envision integrating Learning analytics (LA) algorithms with learning systems based on big data. Learning analytics (LA) represent a set of algorithms useful for the analysis and pre-processing of the massive data originally generated in the MOOCs. Indeed, we find two approaches: one supervised and another unsupervised [4,5]. On the other side, big data represent the tendency of actors to store massive data of different natures and to process them in parallel in tune with an architecture [6] built on three key elements: HDSF, MapReduce and YARN. Research problematicThe massive data generated by the services which are offered within the MOOCs systems are structured, semi-structured and unstructured. Given such fact, prerequisite is to make an in-depth analysis focusing on all the massive data dimensions. To this end, the author in [7] identifies three dimensio...

An important part of education is student's learning. Good quality education is based mainly on how well student attain the knowledge. One way to achieve that is to simplify the content and make it as intuitive as possible. This can be challenging especially for introductory computer science courses for non-computer science students. Such courses are supposed to cover a wide range of complex computer concepts such as networking, computer internal hardware, databases, operating systems and others.In this paper we are presenting the results of a study done on the use of YouTube videos to enhance students' learning. We have evaluated the student's performance in an introduction to computers course for non-computer science students by comparing two groups of students, The first one is a test group in which we have supplied the students with a set of videos from YouTube to illustrate different concepts such as multiple core versus single core processor, hard disk internal components, using fiber optic cables to connect continents under water..ect. The second is a control group in which we have only used the traditional resources, such as the textbook, in class lectures and handouts. The results of the study have shown that students understand and can remember the complex concepts much better when they are exposed to a visual explanation video. We found that most of the students if not all watched the short videos, which is not the case with textual content. One of the main advantages of YouTube is that it is a free web based service that contains short contents about specific concepts taught in schools. Educators can easily search and review videos related to a specific concept or knowledge, and then provide the students with the link. In our case the videos were downloaded using RealPlayer plugin, which allowed us to download any video streaming content on the web. Then we have uploaded the videos in our LMS (learning management system). We have opted to include the videos in the LMS so that we can track the number of students who have downloaded the videos and keep track of the number of downloads. In this study we have found that using YouTube videos encouraged students to look for similar videos, and get a habit of using YouTube as an educational resource. The only challenge is the evaluation of the reliability of the content, for that reason content selection has to done by the instructor.

Background: Video games are very well known for their intrinsic adaptivity; as they adapt the gameplay to the player’s preferences and rhythm. In addition to adapting the gameplay, educational games should also adapt the learning content to match the learner’s competencies, preferences, playing and learning styles. Determining the playing style in an educational game is made possible by collecting certain metrics and information susceptible of monitoring the player’s interactions in the game. However, it is still a challenge to assess the learner’s learning style. Aim: This study examines the correlation between learning and playing styles. It has been acknowledged that both playing and learning styles are related to personality. After examining the personality traits of each style of both Kolb’s learning styles and Bartle’s playing styles, it was hypothesized that there would be a correlation between the two. In that purpose, a quantitative research was conducted to explore the relationship between the two taxonomies. Method: One hundred high school students majoring in science in Morocco have completed Kolb’s learning style inventory (version 3.1) as well as the Bartle test questionnaire developed by Andreasen and Downey. The statistical correlation between the two taxonomies was investigated using cross-tabulation, Chi-square/Fisher’s exact test and Pearson coefficient. Results: Results revealed a relevant interdependency between Kolb’s learning styles and Bartle’s playing styles. The ‘convergent’ type was found to correlate with Bartle’s explorer type; the majority of assimilators adopt the killer type in a game; accomodators tend to be achievers and divergers prefer to be socializers. In terms of learning styles, it was noticed that the majority of participants adopted the converging and the assimilating learning styles; which is in line with what it is indicated in Kolb’s inventory. Results have also shown that learning and playing styles are gender independent. It was concluded that the learning style can be predicted, based on the playing style.

Due to the lack of face to face interaction in online learning environment, this article aims essentially to give tutors the opportunity to understand and analyze learners’ cognitive behavior. In this perspective, we propose an automatic system to assess learners’ cognitive presence regarding their social interactions within synchronous online discussions. Combining Natural Language Preprocessing, Doc2Vec document embedding method and machine learning techniques; we first make some transformations and preprocessing to the given transcripts, then we apply Doc2Vec method to represent each message as a vector that will be concatenated with LIWC and context features. The vectors are input data of Naïve Bayes algorithm; a machine learning method; that aims to classify transcripts according to cognitive presence categories.